Incremental Evolution in ANNs: Neural Nets which Grow

This paper explains the optimisation of neuralnetwork topology using Incremental Evolution;that is, by allowing the network to expand byadding to its structure. This method allows anetwork to grow from a simple to a complexstructure until it is capable of fulfilling itsintended function. The approach is somewhatanalogous to the growth of an embryo or theevolution of a fossil line through time, it istherefore sometimes referred to as anembryology or embryological algorithm. Thepaper begins with a general introduction,comparing this method to other competingtechniques such as The Genetic Algorithm, otherEvolutionary Algorithms and SimulatedAnnealing. A literature survey of previous workis included, followed by an extensive newframework for application of the technique.Finally, examples of applications and a generaldiscussion are presented.

[1]  E. Alpaydin,et al.  Comparing distributed and local neural classifiers for the recognition of Japanese phonemes , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[2]  Christopher MacLeod.  The synthesis of artificial neural networks using single string evolutionary techniques , 1999 .

[3]  Karl E. Kürten,et al.  Pattern-specific neural network design , 1995 .

[4]  R. K. Brouwer,et al.  Automatic growing of a Hopfield style neural network for classification of patterns , 1995 .

[5]  C. Jutten,et al.  Gal: Networks That Grow When They Learn and Shrink When They Forget , 1991 .

[6]  R. Kozma,et al.  Dynamic structure adaptation in feedforward neural networks-an example of plant monitoring , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[7]  Sung-Mo Kang,et al.  A modified Hopfield network for two-dimensional module placement , 1990, IEEE International Symposium on Circuits and Systems.

[8]  D. Palmer-Brown.  High-speed Learning in a Supervised, Self-growing Net. , 1992 .

[9]  Chin-Teng Lin,et al.  FALCON: a fuzzy adaptive learning control network , 1994, NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intellige.

[10]  Patrick K. Simpson,et al.  Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations , 1990 .

[11]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[12]  S. Grossberg,et al.  Neural Dynamics of Category Learning and Recognition: Attention, Memory Consolidation, and Amnesia , 1987 .

[13]  Eric B. Baum,et al.  A Proposal for More Powerful Learning Algorithms , 1989, Neural Computation.

[14]  Timur Ash,et al.  Dynamic node creation in backpropagation networks , 1989 .

[15]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[16]  Donald E. Waagen,et al.  Neural Network Construction Using Evolutionary Search. , 1994 .

[17]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[18]  Sujoy Ghose,et al.  Growing nonuniform feedforward networks for continuous mappings , 1996, Neurocomputing.

[19]  Adrian Thompson,et al.  Silicon evolution , 1996 .

[20]  R. P. J. Perazzo,et al.  Asymptotic Inferential Capabilities of Feed-Forward Neural Networks , 1991 .

[21]  Shoichi Noguchi,et al.  A growing network that optimizes between undertraining and overtraining , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[22]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[23]  James L. Crowley,et al.  Incremental supervised learning for mobile robot reactive control , 1997, Robotics Auton. Syst..

[24]  Fang Jian,et al.  Neural network design based on evolutionary programming , 1997 .

[25]  Yugeng Xi,et al.  Neural network design based on evolutionary programming , 1997, Artif. Intell. Eng..